Data Scientist and AI Engineer, Harare

Data Scientist and AI Engineer at AI Creative Solutions in Harare. I build the data foundation an organisation runs on and the intelligence layer on top of it: ERP pipelines, lakes and warehouses, machine learning, and governed AI agents in production. My independent research works on the gap between models that excel in well-resourced conditions and models that hold up in the real world.

View my work Collaborate CV (PDF)

3× Microsoft CertifiedZindi Ambassador, ZimbabweFeatured in ITU NewsIndabaX Best Poster 2026Deep Learning Indaba 2027 (selected)

NowData Scientist and AI Engineer at AI Creative Solutions. Open to research collaboration, mentoring and speaking.

Recognition

University World NewsITU NewsIndabaX ZimbabweDeep Learning Indaba 2027 (selected)Zindi

01 Selected work

Data science, put into production.

Computer visionlive

BroilerVision: computer vision for broiler houses

An overhead camera, a detector and a dashboard for the stockperson: it counts broilers with an honest range and flags any bird that stops moving.

YOLO11nONNXPythonStreamlit

AI engineeringLive demo

Internal knowledge assistant: answers with sources, or an honest refusal

Answers staff questions only from the company's documents, cites the source behind every claim, and refuses when the documents cannot support an answer.

PythonFastAPIHybrid retrievalLlama 3.1Streamlit

Applied AI researchongoing

ZimCropGuard: multi-crop disease detection under domain shift

Ongoing research on multi-crop disease detection under real African field conditions. Best Poster, Deep Learning IndabaX Zimbabwe 2026.

Best Poster IndabaX 20265 crops 21+ classes54K+ training images

PyTorchEfficientNetB0ViT-B/16StreamlitPWA

AI engineering

AI agent orchestration

AI agents that answer questions on live business data within each user's permissions, with evidence for every figure and decisions left to people.

MindStudioClaudePostgreSQLTypeScriptReact

Data engineering

Live ERP integration and data pipelines

ERP and accounting data brought into lakes and warehouses without disturbing daily work, and checked before anyone relies on it.

SAP Business OneSagePostgreSQLT-SQLTypeScript

Machine learning researchLive demo

Tomato leaf disease detection: hybrid CNN-Transformer

My completed BSc Honours dissertation, deployed as a live Streamlit demo: a hybrid CNN-Transformer built to close the lab-to-field gap on budget phones.

+36pt low-light F1 gainLive Streamlit demoDeployed BSc Honours dissertation

PyTorchResNet18TransformerStreamlitscikit-learn

From my public data projectsDurban port calls, last 90 daysUpdated weekly · to 16 October 2026

View all work →

By the numbers